English
Related papers

Related papers: Chain-of-Thought Hijacking

200 papers

Aligning large language models (LLMs) with human values, particularly when facing complex and stealthy jailbreak attacks, presents a formidable challenge. Unfortunately, existing methods often overlook this intrinsic nature of jailbreaks,…

Computation and Language · Computer Science 2024-12-17 Yuqi Zhang , Liang Ding , Lefei Zhang , Dacheng Tao

Large Reasoning Models (LRMs) have significantly improved problem-solving through explicit Chain-of-Thought (CoT) reasoning. However, this capability creates a Safety-Helpfulness Paradox: the reasoning process itself can be misused to…

Artificial Intelligence · Computer Science 2026-01-27 Xin Gao , Shaohan Yu , Zerui Chen , Yueming Lyu , Weichen Yu , Guanghao Li , Jiyao Liu , Jianxiong Gao , Jian Liang , Ziwei Liu , Chenyang Si

Multimodal Large Language Models (MLLMs) have become widely deployed, yet their safety alignment remains fragile under adversarial inputs. Previous work has shown that increasing inference steps can disrupt safety mechanisms and lead MLLMs…

Computer Vision and Pattern Recognition · Computer Science 2026-04-17 Xiangdong Hu , Yangyang Jiang , Qin Hu , Xiaojun Jia

Large Reasoning Models (LRMs) allocate substantial inference-time compute to Chain-of-Thought (CoT) reasoning, improving performance on mathematics, scientific QA, and tool usage. However, this introduces overthinking: LRMs often reach a…

Computation and Language · Computer Science 2026-04-21 Sangjun Song , Minjae Oh , Seungkyu Lee , Sungmin Jo , Yohan Jo

Large reasoning models (LRMs) produce complex, multi-step reasoning traces, yet safety evaluation remains focused on final outputs, overlooking how harm emerges during reasoning. When jailbroken, harm does not appear instantaneously but…

Computation and Language · Computer Science 2026-04-22 Ishita Kakkar , Enze Zhang , Rheeya Uppaal , Junjie Hu

Research on jailbreaking has been valuable for testing and understanding the safety and security issues of large language models (LLMs). In this paper, we introduce Iterative Refinement Induced Self-Jailbreak (IRIS), a novel approach that…

Cryptography and Security · Computer Science 2024-10-17 Govind Ramesh , Yao Dou , Wei Xu

While significant attention has been dedicated to exploiting weaknesses in LLMs through jailbreaking attacks, there remains a paucity of effort in defending against these attacks. We point out a pivotal factor contributing to the success of…

Computation and Language · Computer Science 2024-06-13 Zhexin Zhang , Junxiao Yang , Pei Ke , Fei Mi , Hongning Wang , Minlie Huang

Despite their strengths, large language models (LLMs) often fail to communicate their confidence accurately, making it difficult to assess when they might be wrong and limiting their reliability. In this work, we demonstrate that reasoning…

Artificial Intelligence · Computer Science 2025-10-23 Dongkeun Yoon , Seungone Kim , Sohee Yang , Sunkyoung Kim , Soyeon Kim , Yongil Kim , Eunbi Choi , Yireun Kim , Minjoon Seo

Large Language Models (LLMs), despite advanced general capabilities, still suffer from numerous safety risks, especially jailbreak attacks that bypass safety protocols. Understanding these vulnerabilities through black-box jailbreak…

Cryptography and Security · Computer Science 2025-05-29 Yao Huang , Yitong Sun , Shouwei Ruan , Yichi Zhang , Yinpeng Dong , Xingxing Wei

Large language models (LLMs) are shown to benefit from chain-of-thought (COT) prompting, particularly when tackling tasks that require systematic reasoning processes. On the other hand, COT prompting also poses new vulnerabilities in the…

Cryptography and Security · Computer Science 2024-01-24 Zhen Xiang , Fengqing Jiang , Zidi Xiong , Bhaskar Ramasubramanian , Radha Poovendran , Bo Li

The challenge of ensuring Large Language Models (LLMs) align with societal standards is of increasing interest, as these models are still prone to adversarial jailbreaks that bypass their safety mechanisms. Identifying these vulnerabilities…

Computation and Language · Computer Science 2025-04-29 Mohammad Akbar-Tajari , Mohammad Taher Pilehvar , Mohammad Mahmoody

In the era of rapid generative AI development, interactions with large language models (LLMs) pose increasing risks of misuse. Prior research has primarily focused on attacks using template-based prompts and optimization-oriented methods,…

Cryptography and Security · Computer Science 2026-03-03 Wenhan Chang , Tianqing Zhu , Yu Zhao , Shuangyong Song , Ping Xiong , Wanlei Zhou

Large reasoning models (LRMs) have emerged as a significant advancement in artificial intelligence, representing a specialized class of large language models (LLMs) designed to tackle complex reasoning tasks. The defining characteristic of…

Computation and Language · Computer Science 2025-07-25 Biao Yi , Zekun Fei , Jianing Geng , Tong Li , Lihai Nie , Zheli Liu , Yiming Li

Large Language Models (LLMs) can be used to red team other models (e.g. jailbreaking) to elicit harmful contents. While prior works commonly employ open-weight models or private uncensored models for doing jailbreaking, as the…

Large reasoning models (LRMs) generate chain-of-thought (CoT) traces before producing final outputs, introducing a dynamic internal state that may complicate control mechanisms such as refusal. Unlike instruction-tuned LLMs, where refusal…

Artificial Intelligence · Computer Science 2026-05-27 Kia-Jüng Yang , Dominik Meier , Jiachen Zhao , Terry Ruas , Bela Gipp

Large Language Models have shown impressive generative capabilities across diverse tasks, but their safety remains a critical concern. Existing post-training alignment methods, such as SFT and RLHF, reduce harmful outputs yet leave LLMs…

Cryptography and Security · Computer Science 2025-10-21 Zhengyue Zhao , Yingzi Ma , Somesh Jha , Marco Pavone , Patrick McDaniel , Chaowei Xiao

The increasing sophistication of large vision-language models (LVLMs) has been accompanied by advances in safety alignment mechanisms designed to prevent harmful content generation. However, these defenses remain vulnerable to sophisticated…

Cryptography and Security · Computer Science 2026-04-09 Quanchen Zou , Zonghao Ying , Moyang Chen , Wenzhuo Xu , Yisong Xiao , Yakai Li , Deyue Zhang , Dongdong Yang , Zhao Liu , Xiangzheng Zhang

Large Reasoning Models (LRMs) achieve impressive performance on complex reasoning tasks via Chain-of-Thought (CoT) reasoning, which enables them to generate intermediate thinking tokens before arriving at the final answer. However, LRMs…

Machine Learning · Computer Science 2026-05-15 Alliot Nagle , Jakhongir Saydaliev , Dhia Garbaya , Michael Gastpar , Ashok Vardhan Makkuva , Hyeji Kim

Despite the remarkable performance of Large Language Models (LLMs), they remain vulnerable to jailbreak attacks, which can compromise their safety mechanisms. Existing studies often rely on brute-force optimization or manual design, failing…

Computation and Language · Computer Science 2025-06-30 Haoming Yang , Ke Ma , Xiaojun Jia , Yingfei Sun , Qianqian Xu , Qingming Huang

Reasoning-oriented Large Language Models (LLMs) often rely on generating explicit tokens step by step, and their effectiveness typically hinges on large-scale supervised fine-tuning or reinforcement learning. While Chain-of-Thought (CoT)…

Computation and Language · Computer Science 2025-09-30 Haoyu Zheng , Zhuonan Wang , Yuqian Yuan , Tianwei Lin , Wenqiao Zhang , Zheqi Lv , Juncheng Li , Siliang Tang , Yueting Zhuang , Hongyang He